公开(公告)号：US09613297B1

公开(公告)日：2017-04-04

申请号：US14980494

申请日：2015-12-28

Applicant: Google Inc.

Inventor： Marc'Aurelio Ranzato

IPC: G06K9/62

CPC classification number: G06K9/6255 ,  G06K9/3241 ,  G06K9/4628 ,  G06K9/6227 ,  G06K9/6268 ,  G06K9/628 ,  G06N3/0454

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying objects in images. One of the methods includes receiving an input image; down-sampling the input image to generate a second image; generating a respective first score for each of the plurality of object categories; selecting an initial patch of the input image; generating a respective second score for each of the plurality of object categories; and generating a respective third score for each of the plurality of object categories from the first scores and the second scores, wherein the respective third score for each of the plurality of object categories represents a likelihood that the input image contains an image of an object belonging to the object category.

公开(公告)号：US09224068B1

公开(公告)日：2015-12-29

申请号：US14096255

申请日：2013-12-04

Applicant: Google Inc.

Inventor： Marc'Aurelio Ranzato

IPC: G06K9/62

CPC classification number: G06K9/6255 ,  G06K9/3241 ,  G06K9/4628 ,  G06K9/6227 ,  G06K9/6268 ,  G06K9/628 ,  G06N3/0454

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying objects in images. One of the methods includes receiving an input image; down-sampling the input image to generate a second image; generating a respective first score for each of the plurality of object categories; selecting an initial patch of the input image; generating a respective second score for each of the plurality of object categories; and generating a respective third score for each of the plurality of object categories from the first scores and the second scores, wherein the respective third score for each of the plurality of object categories represents a likelihood that the input image contains an image of an object belonging to the object category.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于识别图像中的对象。 其中一种方法包括接收输入图像; 对输入图像进行下采样以产生第二图像; 为所述多个对象类别中的每一个生成相应的第一分数; 选择输入图像的初始贴片; 为所述多个对象类别中的每一个生成相应的第二分数; 以及从所述第一分数和所述第二分数生成针对所述多个对象类别中的每一个的相应第三分数，其中，所述多个对象类别中的每一个的相应第三分数表示所述输入图像包含所属对象的图像的似然性 到对象类别。

公开(公告)号：US09852363B1

公开(公告)日：2017-12-26

申请号：US14987955

申请日：2016-01-05

Applicant: Google Inc.

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Gregory Sean Corrado ,  Marc'Aurelio Ranzato

IPC: G06K9/62 ,  G06F17/30

CPC classification number: G06K9/627 ,  G06F17/30244 ,  G06F17/30247 ,  G06F17/30268 ,  G06F17/3079 ,  G06F17/30843 ,  G06K9/6215 ,  G06K9/6255 ,  G06K9/6256

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating labeled images. One of the methods includes selecting a plurality of candidate videos from videos identified in a response to a search query derived from a label for an object category; selecting one or more initial frames from each of the candidate videos; detecting one or more initial images of objects in the object category in the initial frames; for each initial frame including an initial image of an object in the object category, tracking the object through surrounding frames to identify additional images of the object; and selecting one or more images from the one or more initial images and one or more additional images as database images of objects belonging to the object category.

公开(公告)号：US09256807B1

公开(公告)日：2016-02-09

申请号：US13803642

申请日：2013-03-14

Applicant: Google Inc.

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Gregory S. Corrado ,  Marc'Aurelio Ranzato

IPC: G06K9/62 ,  G06F17/30

CPC classification number: G06K9/627 ,  G06F17/30244 ,  G06F17/30247 ,  G06F17/30268 ,  G06F17/3079 ,  G06F17/30843 ,  G06K9/6215 ,  G06K9/6255 ,  G06K9/6256

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating labeled images. One of the methods includes selecting a plurality of candidate videos from videos identified in a response to a search query derived from a label for an object category; selecting one or more initial frames from each of the candidate videos; detecting one or more initial images of objects in the object category in the initial frames; for each initial frame including an initial image of an object in the object category, tracking the object through surrounding frames to identify additional images of the object; and selecting one or more images from the one or more initial images and one or more additional images as database images of objects belonging to the object category.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于生成标记图像。 方法之一包括从对于从对象类别的标签导出的搜索查询的响应中识别的视频中选择多个候选视频; 从每个候选视频中选择一个或多个初始帧; 检测初始帧中对象类别中的对象的一个​​或多个初始图像; 对于包括对象类别中的对象的初始图像的每个初始帧，通过周围帧跟踪对象以识别对象的附加图像; 以及从一个或多个初始图像和一个或多个附加图像中选择一个或多个图像作为属于对象类别的对象的数据库图像。

公开(公告)号：US09202464B1

公开(公告)日：2015-12-01

申请号：US13859692

申请日：2013-04-09

Applicant: Google Inc.

Inventor： Andrew William Senior ,  Marc'Aurelio Ranzato

IPC: G10L15/00 ,  G06F15/18 ,  G10L15/16 ,  G06N3/02

CPC classification number: G06N3/02 ,  G06N3/08 ,  G10L15/063 ,  G10L2015/0631

Abstract: Methods and apparatus related to training speech recognition devices are presented. A computing device receives training samples for training a neural network to learn an acoustic speech model. A curriculum function for speech modeling can be determined. For each training sample of the training samples, a corresponding curriculum function value for the training sample can be determined using the curriculum function. The training samples can be ordered based on the corresponding curriculum function values. In some embodiments, the neural network can be trained utilizing the ordered training samples. The trained neural network can receive an input of a second plurality of samples corresponding to human speech, where the second plurality of samples differs from the training samples. In response to receiving the second plurality of samples, the trained neural network can generate a plurality of phones corresponding to the captured human speech.

Abstract translation: 提出了与训练语音识别装置相关的方法和装置。 计算设备接收用于训练神经网络的训练样本以学习声学语音模型。 可以确定语音建模的课程功能。 对于训练样本的每个训练样本，可以使用课程功能确定训练样本的相应课程功能值。 训练样本可以根据相应的课程功能值进行排序。 在一些实施例中，可以使用有序训练样本训练神经网络。 所训练的神经网络可以接收对应于人类语音的第二多个样本的输入，其中第二多个样本与训练样本不同。 响应于接收到第二多个样本，经训练的神经网络可以产生对应于所捕获的人类语音的多个电话。

公开(公告)号：US09129190B1

公开(公告)日：2015-09-08

申请号：US14096234

申请日：2013-12-04

Applicant: Google Inc.

Inventor： Marc'Aurelio Ranzato

IPC: G06K9/62

CPC classification number: G06K9/6257 ,  G06N3/0454

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying objects in images. One of the methods includes obtaining a first training image; down-sampling the first training image to generate a low-resolution first training image; processing the low-resolution first training image using a first neural network to generate a plurality of features of the low-resolution first training image and first scores for the low-resolution first training image; processing the first scores and the features of the low-resolution first training image using an initial patch locator neural network to generate an initial location of an initial patch of the first training image; locally perturbing the initial location to select an adjusted location for the initial patch of the first training image; and updating the current values of the parameters of the initial patch locator neural network to generate updated values using the adjusted location.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于识别图像中的对象。 其中一种方法包括获得第一训练图像; 对第一训练图像进行下采样以产生低分辨率第一训练图像; 使用第一神经网络处理所述低分辨率第一训练图像以生成所述低分辨率第一训练图像的多个特征和所述低分辨率第一训练图像的第一分数; 使用初始片段定位器神经网络处理所述低分辨率第一训练图像的第一分数和特征，以生成所述第一训练图像的初始片段的初始位置; 局部扰动初始位置以选择第一训练图像的初始补片的调整位置; 并且使用调整的位置更新初始补丁定位器神经网络的参数的当前值以生成更新的值。